Getting Started

This guide will walk you through the process of setting up and using the Tiptree Platform for the first time.

Prerequisites

Before you begin, ensure you have:

• A Tiptree Platform account (for the managed service) or a self-hosted installation
• API credentials (API key or OAuth client credentials)
• Python 3.8+ or Node.js 14+ for using the client libraries

Installation

Python Client

Install the Python client library using pip:

pip install tiptree-client

TypeScript/JavaScript Client

Install the TypeScript client using npm or yarn:

npm install @tiptree/client
# or
yarn add @tiptree/client

Authentication

Using API Keys

# Python
from tiptree.client import TiptreeClient

client = TiptreeClient(api_key="your-api-key")

// TypeScript
import { TiptreeClient } from '@tiptree/client';

const client = new TiptreeClient({
  apiKey: 'your-api-key'
});

Using OAuth

# Python
from tiptree.client import TiptreeClient

client = TiptreeClient(
    client_id="your-client-id",
    client_secret="your-client-secret"
)

// TypeScript
import { TiptreeClient } from '@tiptree/client';

const client = new TiptreeClient({
  clientId: 'your-client-id',
  clientSecret: 'your-client-secret'
});

Creating Your First Agent

Agents are the core building blocks of the Tiptree Platform. Here’s how to create a simple agent:

# Python
agent = client.agents.create(
    name="My First Agent",
    description="A simple agent for testing",
    model="gpt-4",
    system_prompt="You are a helpful assistant that provides concise answers."
)

print(f"Agent created with ID: {agent.id}")

// TypeScript
const agent = await client.agents.create({
  name: "My First Agent",
  description: "A simple agent for testing",
  model: "gpt-4",
  systemPrompt: "You are a helpful assistant that provides concise answers."
});

console.log(`Agent created with ID: ${agent.id}`);

Starting a Session

To interact with an agent, you need to create a session:

# Python
session = client.sessions.create(agent_id=agent.id)
print(f"Session created with ID: {session.id}")

// TypeScript
const session = await client.sessions.create({
  agentId: agent.id
});

console.log(`Session created with ID: ${session.id}`);

Sending Messages

Once you have a session, you can send messages to the agent:

# Python
response = client.messages.send(
    session_id=session.id,
    content="What's the capital of France?"
)

print(f"Agent response: {response.content}")

// TypeScript
const response = await client.messages.send({
  sessionId: session.id,
  content: "What's the capital of France?"
});

console.log(`Agent response: ${response.content}`);

Retrieving Message History

You can retrieve the message history for a session:

# Python
messages = client.messages.list(session_id=session.id)
for message in messages:
    print(f"{message.role}: {message.content}")

// TypeScript
const messages = await client.messages.list({
  sessionId: session.id
});

messages.forEach(message => {
  console.log(`${message.role}: ${message.content}`);
});

Using Agent Tools

Agents can be configured with tools to perform actions:

# Python
agent_with_tools = client.agents.create(
    name="Weather Agent",
    description="An agent that can check the weather",
    model="gpt-4",
    system_prompt="You are a helpful assistant that can check the weather.",
    tools=[
        {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    }
                },
                "required": ["location"]
            }
        }
    ]
)

// TypeScript
const agentWithTools = await client.agents.create({
  name: "Weather Agent",
  description: "An agent that can check the weather",
  model: "gpt-4",
  systemPrompt: "You are a helpful assistant that can check the weather.",
  tools: [
    {
      name: "get_weather",
      description: "Get the current weather for a location",
      parameters: {
        type: "object",
        properties: {
          location: {
            type: "string",
            description: "The city and state, e.g. San Francisco, CA"
          }
        },
        required: ["location"]
      }
    }
  ]
});

Next Steps

Now that you’ve created your first agent and interacted with it, you can:

• Explore the API Reference for more advanced features
• Learn about Agent Configuration options
• Understand Error Handling for robust applications